# StyleDGPT: Stylized Response Generation with Pre-trained Language Models

arXiv: https://arxiv.org/abs/2010.02569 · HTML: https://mlsanity.com/paper/2010.02569/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Black-box Prompt Learning for Pre-trained Language Models](https://mlsanity.com/paper/2201.08531/) (2022)
- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories](https://mlsanity.com/paper/2306.05406/) (2023)
- [Modulating Language Models with Emotions](https://mlsanity.com/paper/2108.07886/) (2021)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation](https://mlsanity.com/paper/2403.11439/) (2024)
- [Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting](https://mlsanity.com/paper/2204.05610/) (2022)
- [Hashtag-Guided Low-Resource Tweet Classification](https://mlsanity.com/paper/2302.10143/) (2023)
- [Micro Language Models Enable Instant Responses](https://mlsanity.com/paper/2604.19642/) (2026)

## Abstract (arXiv)

Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training. In this work, we explore the challenging task with pre-trained language models that have brought breakthrough to various natural language tasks. To this end, we introduce a KL loss and a style classifier to the fine-tuning step in order to steer response generation towards the target style in both a word-level and a sentence-level. Comprehensive empirical studies with two public datasets indicate that our model can significantly outperform state-of-the-art methods in terms of both style consistency and contextual coherence.